Investigating the Impact of Environment and Data Aggregation by Walking Bout Duration on Parkinson's Disease Classification Using Machine Learning.
Investigating the Impact of Environment and Data Aggregation by Walking Bout Duration on Parkinson's Disease Classification Using Machine Learning.
复制标题
DOI：
10.3389/fnagi.2022.808518
复制
发表时间：
2022
影响因子：
4.8
通讯作者：
Del Din S
中科院分区：
文献类型：
--
作者：
Rehman RZU;Guan Y;Shi JQ;Alcock L;Yarnall AJ;Rochester L;Del Din S
帕金森病(PD)是一种常见的神经退行性疾病。帕金森病可在早期误诊。帕金森病的步态障碍是典型的，与跌倒风险增加和生活质量下降有关。与实验室数据相比，将机器学习(ML)模型应用于真实世界的步态可能会更敏感地对PD进行分类。真实世界的步态会产生多个步行回合(WBS)，选择最优的方法来聚集数据(例如，不同的WB持续时间)是至关重要的，因为这可能会影响分类性能。本研究的目的是调查环境(实验室与真实世界)和数据聚合对ML性能的影响，以优化PD分类的敏感度。对47例帕金森病患者(年龄：68±9岁)和52例对照组(健康对照组，年龄：70±7岁)进行步态评估。在实验室中，参与者以正常速度行走2分钟，而在现实世界中，参与者被评估超过7天。在这两种环境中，14个步态特征通过一个安装在下背部的三轴加速度计进行了评估。用曲线下面积(AUC)评价个体步态特征区分PD和HC的能力。与实验室数据相比，应用于真实步态的ML模型(即支持向量机模型、随机森林模型和集成模型)具有更好的分类性能。与实验室步态特征(0.51≤AUC≤0.77)相比，真实世界步态特征在较长的WBS(WB 30-60 S，WB>；60 S，WB>；120 S)中聚集的结果导致了更好的区分性能(PD与HC)。真实世界的步态速度显示出最高的AUC为0.77。总体而言，根据WBS>；60 S的14个步态特征进行随机森林训练的结果(F1分数=77.20±5.51%)比实验室结果(F1分数=68.75±12.80%)要好。这项研究的结果表明，环境的选择和数据聚合对于实现最大限度的区分性能非常重要，并直接影响PD分类的ML性能。这项研究强调了协调一致的数据分析方法的重要性，以推动未来的实施和临床应用。[09/H0906/82]。
Parkinson’s disease (PD) is a common neurodegenerative disease. PD misdiagnosis can occur in early stages. Gait impairment in PD is typical and is linked with an increased fall risk and poorer quality of life. Applying machine learning (ML) models to real-world gait has the potential to be more sensitive to classify PD compared to laboratory data. Real-world gait yields multiple walking bouts (WBs), and selecting the optimal method to aggregate the data (e.g., different WB durations) is essential as this may influence classification performance. The objective of this study was to investigate the impact of environment (laboratory vs. real world) and data aggregation on ML performance for optimizing sensitivity of PD classification. Gait assessment was performed on 47 people with PD (age: 68 ± 9 years) and 52 controls [Healthy controls (HCs), age: 70 ± 7 years]. In the laboratory, participants walked at their normal pace for 2 min, while in the real world, participants were assessed over 7 days. In both environments, 14 gait characteristics were evaluated from one tri-axial accelerometer attached to the lower back. The ability of individual gait characteristics to differentiate PD from HC was evaluated using the Area Under the Curve (AUC). ML models (i.e., support vector machine, random forest, and ensemble models) applied to real-world gait showed better classification performance compared to laboratory data. Real-world gait characteristics aggregated over longer WBs (WB 30–60 s, WB > 60 s, WB > 120 s) resulted in superior discriminative performance (PD vs. HC) compared to laboratory gait characteristics (0.51 ≤ AUC ≤ 0.77). Real-world gait speed showed the highest AUC of 0.77. Overall, random forest trained on 14 gait characteristics aggregated over WBs > 60 s gave better performance (F1 score = 77.20 ± 5.51%) as compared to laboratory results (F1 Score = 68.75 ± 12.80%). Findings from this study suggest that the choice of environment and data aggregation are important to achieve maximum discrimination performance and have direct impact on ML performance for PD classification. This study highlights the importance of a harmonized approach to data analysis in order to drive future implementation and clinical use. [09/H0906/82].
登录
查看更多内容
影响因子：
7.4
作者：
Evers LJ;Raykov YP;Krijthe JH;Silva de Lima AL;Badawy R;Claes K;Heskes TM;Little MA;Meinders MJ;Bloem BR
通讯作者：
Bloem BR
影响因子：
4.3
作者：
Emamzadeh FN;Surguchov A
通讯作者：
Surguchov A
影响因子：
4.8
作者：
Hobert, Markus A.;Nussbaum, Susanne;Heinzel, Sebastian
通讯作者：
Heinzel, Sebastian
DOI：
10.1093/gerona/gls255
发表时间：
2013-07-01
影响因子：
5.1
作者：
Lord, Sue;Galna, Brook;Rochester, Lynn
通讯作者：
Rochester, Lynn
影响因子：
4.1
作者：
Lawson RA;Yarnall AJ;Duncan GW;Breen DP;Khoo TK;Williams-Gray CH;Barker RA;Collerton D;Taylor JP;Burn DJ;ICICLE-PD study group
通讯作者：
ICICLE-PD study group